Trusted-AI/adversarial-robustness-toolbox — GitHub trend

FINDING #6475 · UNIT ID 125381318

Trusted-AI/adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0007

ENGAGEMENT0.48

FRESHNESS1.00

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

0% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

2.43

ACCEL

+0.07

RETENTION

33.3%

PEAK 2026-10-14 · FORK-RETENTION 0.0% · 17 STARS / WINDOW

Author Audience

AUDIENCE

3,431

FOLLOWERS

619

OWNER ★

10,967

Engagement Signals

FORKS

1,348

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 17 / 17 (DIVERSITY 1.00)

Why This Is A Finding

Trusted-AI/adversarial-robustness-toolbox собрал 17 звёзд за окно, тогда как у автора всего 619 подписчиков — эффективная аудитория ≈ 3,431. Это даёт surprise-индекс 0.0007 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 33% OF 9651 FINDINGS

#02Oldcircle/geo-sleuth[ PYTHON ]0.78 #05Arekejoker/qwen21-nsfw-pose-skill[ PYTHON ]0.64 #31ardeyouxipianyi/workbuddy2api-hub[ PYTHON ]0.35 #38AsherJN/recall[ PYTHON ]0.31 #40MerZlin/dsh-pet-indesktop[ PYTHON ]0.30

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9651 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 33%

VELOCITY2.433.14-0.71ABOVE 36%

RETENTION33.3%16.7%+16.7 PPABOVE 67%

FORKS1,348277+1,071ABOVE 79%

SURPRISE0.000.00-0.00ABOVE 25%